Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already establishes that this is a safe read operation, so the description's job is to add context beyond that. It does: it discloses the main return fields (risk_score range, IP risk, disposition, remaining query funds), notes the cost tier, and supplies the POST endpoint, though it omits interpretation guidance for disposition values.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tightly packed sentences: purpose, return values, minimal input guidance, and API endpoint. Nothing is wasted and the most important information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, low schema description coverage, and nested objects, the description supplies the essential framing: what it returns, what to send at minimum, and that it is the cheapest tier. It is reasonably complete for an agent to call it correctly, though disposition interpretation and deeper nested parameter meaning remain absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 18%, so the description must compensate. It does add priority guidance by naming device.ip_address and the email/billing/order objects, but with 11 top-level parameters it leaves most object groups unexplained, so the compensation is partial rather than complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Score a transaction for fraud risk.' The phrase 'the lightest, cheapest assessment' implicitly distinguishes it from the heavier minFraud siblings, but it does not name an alternative tool the way a top-tier definition would.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies usage by calling itself the 'lightest, cheapest assessment' and recommends sending at least device.ip_address. However, it never states when to choose this over minfraud_factors or minfraud_insights, nor any when-not-to-use condition.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.